What I Build
Building retrieval systems that surface the right context at the right time.
Multi-agent workflows with LangGraph, Autogen, and custom frameworks.
Connecting LLMs to APIs, databases, and external systems.
Building metrics and benchmarks to measure AI system performance.
Customizing models for domain-specific tasks and behaviors.
Shipping AI systems that scale reliably in production environments.
Systems & Solutions
Users were frustrated by the 'tab fatigue' of booking flights, hotels, and activities across different sites.
Surgeons spent 2+ hours daily on post-op documentation, leading to burnout and delayed billing cycles.
Analysts couldn't synthesize real-time market news with historical SEC filings fast enough to capitalize on intra-day volatility.
Manual inspection of physical device labels and components led to 2% non-compliance, risking FDA audits and costly recalls.
Underwriters had to manually navigate 15+ legacy government portals to verify policyholder data, causing a massive bottleneck in the quote-to-bind funnel.
The client needed to audit thousands of unstructured ESG reports to identify high-risk investments, a process previously requiring weeks of manual analyst labor.
SRE teams were overwhelmed by alert fatigue from thousands of non-critical logs, missing actual root causes during production outages.
Engineering managers were losing 10+ hours a week to manual backlog grooming and identifying blockers across fragmented Slack and Jira threads.
Tools I Work With
Ready to add agentic intelligence to your product?
Schedule a Discovery Call
